© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 63791
    Prev
    Next
    INDEX
    Explanations

    source

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     poderosa
    -0.08
     puiss
    -0.08
     epekto
    -0.08
     establecidos
    -0.08
     Gefühl
    -0.08
     alde
    -0.08
     steigen
    -0.07
     poderoso
    -0.07
     чувство
    -0.07
     potente
    -0.07
    POSITIVE LOGITS
    源码
    0.14
    源
    0.10
    代码
    0.09
    コード
    0.09
    ource
    0.09
    を見る
    0.08
     fuente
    0.08
     المصدر
    0.08
    -written
    0.08
     codigo
    0.08
    Activations Density 0.023%

    No Known Activations